emergent-misalignment / emergent-misalignmentLinks
☆198Updated 5 months ago
Alternatives and similar repositories for emergent-misalignment
Users that are interested in emergent-misalignment are comparing it to the libraries listed below
Sorting:
- Open source interpretability artefacts for R1.☆158Updated 4 months ago
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models☆200Updated last month
- A toolkit for describing model features and intervening on those features to steer behavior.☆198Updated 9 months ago
- Collection of evals for Inspect AI☆211Updated this week
- ☆139Updated last week
- METR Task Standard☆159Updated 6 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆122Updated 6 months ago
- A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning☆251Updated this week
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆261Updated 2 months ago
- open source interpretability platform 🧠☆356Updated last week
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆207Updated this week
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆214Updated 8 months ago
- ☆119Updated 2 weeks ago
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆108Updated last week
- ☆98Updated 4 months ago
- ☆101Updated 5 months ago
- Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'☆229Updated last month
- Improving Alignment and Robustness with Circuit Breakers☆228Updated 11 months ago
- https://transformer-circuits.pub/2025/attribution-graphs/methods.html☆78Updated 5 months ago
- Sparsify transformers with SAEs and transcoders☆609Updated last week
- A simple unified framework for evaluating LLMs☆241Updated 4 months ago
- Functional Benchmarks and the Reasoning Gap☆88Updated 10 months ago
- ControlArena is a collection of settings, model organisms and protocols - for running control experiments.☆88Updated this week
- ☆56Updated 3 weeks ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆173Updated 7 months ago
- ☆406Updated 2 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆124Updated 2 months ago
- Steering Llama 2 with Contrastive Activation Addition☆176Updated last year
- ☆163Updated 9 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆260Updated last year